{"id":"W4396832846","doi":"10.1080/01639374.2024.2347210","title":"Duplicate Records in WorldCat for 20th-Century American, British, and Canadian Books: A Comparison of Duplication Rates and Causes","year":2024,"lang":"en","type":"article","venue":"Cataloging & Classification Quarterly","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Library science; Cataloging; History; Computer science; Information retrieval; Genealogy; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01204936,0.0003746361,0.0009047752,0.04878539,0.003888804,0.005034878,0.00196795,0.0006797477,0.004217851],"category_scores_gemma":[0.07603083,0.0005724546,0.0009329658,0.06606442,0.002379373,0.003170305,0.003222903,0.0007086665,0.001278754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01155696,"about_ca_system_score_gemma":0.0158941,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4191961,"about_ca_topic_score_gemma":0.5122988,"domain_scores_codex":[0.9652948,0.002091837,0.004139744,0.001898482,0.02459464,0.001980505],"domain_scores_gemma":[0.8831846,0.02062668,0.02262268,0.008384484,0.06325978,0.001921816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003561226,0.00005135083,0.7668492,0.001358431,0.0003096473,0.001747884,0.03411084,0.0003809446,0.001076733,0.006675309,0.02194818,0.1651354],"study_design_scores_gemma":[0.00001070165,0.00004459762,0.9349335,0.0005722244,0.0002226163,0.00185138,0.01846462,0.0005737121,0.001780126,0.0007380079,0.04072766,0.0000808582],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.929332,0.01254554,0.002510806,0.001344763,0.0002032302,0.0004837713,0.02454117,0.0004143373,0.0286244],"genre_scores_gemma":[0.9525387,0.009731637,0.003539665,0.0002714161,0.00009793827,0.0002232063,0.02271516,0.0002347688,0.01064752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9949651,"threshold_uncertainty_score":0.8335122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06085712074718828,"score_gpt":0.2895339395762924,"score_spread":0.2286768188291042,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}